Example usage for org.apache.poi.hpsf.wellknown PropertyIDMap PID_AUTHOR

Introduction

In this page you can find the example usage for org.apache.poi.hpsf.wellknown PropertyIDMap PID_AUTHOR.

Prototype

int PID_AUTHOR

To view the source code for org.apache.poi.hpsf.wellknown PropertyIDMap PID_AUTHOR.

Click Source Link

Document

ID of the property that denotes the document's author

Usage

From source file:org.jlibrary.core.search.extraction.MSOfficeExtractor.java

License:Open Source License

/**
 * Returns a map with the extracted meta information from the document.<p>
 * //w w  w .  j  a v  a 2s.co  m
 * @return a map with the extracted meta information from the document
 */
protected HeaderMetaData extractMetaInformation() {

    HeaderMetaData metadata = new HeaderMetaData();
    String meta;
    if (m_summary != null) {
        // can't use convenience methods on summary since they can't deal with multiple sections
        Section section = (Section) m_summary.getSections().get(0);

        meta = (String) section.getProperty(PropertyIDMap.PID_TITLE);
        if ((meta != null) && !meta.equals("")) {
            metadata.setTitle(meta);
            metadata.setDescription(meta);
        }
        meta = (String) section.getProperty(PropertyIDMap.PID_KEYWORDS);
        if ((meta != null) && !meta.equals("")) {
            metadata.setKeywords(meta);
        }
        meta = (String) section.getProperty(PropertyIDMap.PID_SUBJECT);
        if ((meta != null) && !meta.equals("")) {
            metadata.setDescription(meta);
        }
        meta = (String) section.getProperty(PropertyIDMap.PID_COMMENTS);
        if ((meta != null) && !meta.equals("")) {
            // Not handled
        }
        // extract other available meta information
        meta = (String) section.getProperty(PropertyIDMap.PID_AUTHOR);
        if ((meta != null) && !meta.equals("")) {
            metadata.setAuthor(meta);
        }
        Date date;
        date = (Date) section.getProperty(PropertyIDMap.PID_CREATE_DTM);
        if ((date != null) && (date.getTime() > 0)) {
            // Not handled            
        }
        date = (Date) section.getProperty(PropertyIDMap.PID_LASTSAVE_DTM);
        if ((date != null) && (date.getTime() > 0)) {
            // Not handled
        }
    }
    if (m_documentSummary != null) {
        // can't use convenience methods on document since they can't deal with multiple sections
        Section section = (Section) m_documentSummary.getSections().get(0);

        // extract available meta information from document summary
        meta = (String) section.getProperty(PropertyIDMap.PID_COMPANY);
        if ((meta != null) && !meta.equals("")) {
            // Not handled
        }
        meta = (String) section.getProperty(PropertyIDMap.PID_MANAGER);
        if ((meta != null) && !meta.equals("")) {
            // Not handled
        }
        meta = (String) section.getProperty(PropertyIDMap.PID_CATEGORY);
        if ((meta != null) && !meta.equals("")) {
            // Not handled
        }
    }

    return metadata;
}

---

From source file:org.opencms.search.extractors.A_CmsTextExtractorMsOfficeBase.java

License:Open Source License

/**
 * Creates the extraction result for this MS Office document.<p>
 * // w  w w.  ja  v  a  2s  . co m
 * The extraction result contains the raw content, plus additional meta information 
 * as content items read from the MS Office document properties.<p>
 * 
 * @param rawContent the raw content extracted from the document
 * 
 * @return the extraction result for this MS Office document
 */
protected I_CmsExtractionResult createExtractionResult(String rawContent) {

    Map contentItems = new HashMap();
    if (CmsStringUtil.isNotEmpty(rawContent)) {
        contentItems.put(I_CmsExtractionResult.ITEM_RAW, rawContent);
    }

    StringBuffer content = new StringBuffer(rawContent);

    if (m_summary != null) {
        // can't use convenience methods on summary since they can't deal with multiple sections
        Section section = (Section) m_summary.getSections().get(0);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_TITLE),
                I_CmsExtractionResult.ITEM_TITLE, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_KEYWORDS),
                I_CmsExtractionResult.ITEM_KEYWORDS, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_SUBJECT),
                I_CmsExtractionResult.ITEM_SUBJECT, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_COMMENTS),
                I_CmsExtractionResult.ITEM_COMMENTS, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_AUTHOR),
                I_CmsExtractionResult.ITEM_AUTHOR, content, contentItems);
    }
    if (m_documentSummary != null) {
        // can't use convenience methods on document since they can't deal with multiple sections
        Section section = (Section) m_documentSummary.getSections().get(0);
        // extract available meta information from document summary
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_COMPANY),
                I_CmsExtractionResult.ITEM_COMPANY, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_MANAGER),
                I_CmsExtractionResult.ITEM_MANAGER, content, contentItems);
        combineContentItem((String) section.getProperty(PropertyIDMap.PID_CATEGORY),
                I_CmsExtractionResult.ITEM_CATEGORY, content, contentItems);
    }

    // free some memory
    cleanup();

    return new CmsExtractionResult(content.toString(), contentItems);
}

---